{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216854","sets":["1164:8666:10876:10877"]},"path":["10877"],"owner":"44499","recid":"216854","title":["ディープ・ラーニングを用いた手話認識に関する研究－CTC とConformerの比較－"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-01"},"_buckets":{"deposit":"811f3ff8-ab2e-40a6-a8b8-82e993984729"},"_deposit":{"id":"216854","pid":{"type":"depid","value":"216854","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"ディープ・ラーニングを用いた手話認識に関する研究－CTC とConformerの比較－","author_link":["560652","560651","560650","560649","560654","560653"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ディープ・ラーニングを用いた手話認識に関する研究－CTC とConformerの比較－"},{"subitem_title":"A Study on Sign Recognition Using Deep Learning－Comparison between CTC and Conformer－","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"聴覚・言語障害支援(2)","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-01","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"豊田工業高等専門学校専攻科情報科学専攻"},{"subitem_text_value":"国立民族学博物館"},{"subitem_text_value":"国立民族学博物館"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Technology, Toyota Collage Advanced Course Computer Science Course","subitem_text_language":"en"},{"subitem_text_value":"National Museum of Ethnology","subitem_text_language":"en"},{"subitem_text_value":"National Museum of Ethnology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/216854/files/IPSJ-AAC22018008.pdf","label":"IPSJ-AAC22018008.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-AAC22018008.pdf","filesize":[{"value":"1.9 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"52"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"3c3ff537-0fb5-4adb-8cb9-9ba4bc10772e","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Institute of Electronics， Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"磯谷, 光"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"木村, 勉"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"神田, 和幸"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hikaru, Isogai","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tsutomu, Kimura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kazuyuki, Kanda","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12752949","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals， conferences， symposia， etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2432-2431","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では機械学習を用いた手話認識において，手話文中で使用されている単語の認識を目的とする．手話文中に発生する遷移動作を考慮して学習するために，手話文を学習データとして機械学習を行い，学習済みモデルを作成する．本研究では音声認識における手法である Connectionist Temporal Classification (CTC) を組み込んだモデルと，自然言語処理で活用される Transformer を利用した Conformer ネットワークを使用したモデルの 2 つの手法で実験した．最終的にテストデータ全体の認識率は CTC 手法が約 74%，Conformer 手法が約 32% となった．しかし，Conformer 手法の認識結果は過学習のような現象が見られ，正常に動作していない可能性があると考えた．今後は Conformer 手法の改善を進めつつ，Transformer と CTC を組み合わせた新たなアルゴリズムについても検討する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this study, our purpose is to recognize signs using machine learning. In order to take into account the transition motions that occur in a sign sentence, machine learning adopts the sign sentences as training data, and a trained model is created. We experimented two models: one that incorporates Connectionist Temporal Classification (CTC) which is a method used in speech recognition, and the other is a conformer model that uses a transformer used in natural language processing. As the result, the recognition rate for the entire test data was about 74% by the CTC method and about 32% by the Conformer method. However, the recognition results of the Conformer method showed a phenomenon as over-learning, and we estimated that it might worked properly. We will improve the Conformer method and will investigate a new algorithm that combines the Transformer with CTC.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告アクセシビリティ（AAC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"2022-AAC-18"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":216854,"updated":"2025-01-19T15:42:42.163357+00:00","links":{},"created":"2025-01-19T01:17:22.055009+00:00"}